© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-27B
    3. 22-GEMMASCOPE-RES-131K
    4. 66519
    Prev
    Next
    INDEX
    Explanations

    assignment, variable declaration

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Gravity
    -0.94
     devoirs
    -0.86
    striker
    -0.85
    ituaries
    -0.85
    vají
    -0.84
    PEZ
    -0.82
     eficacia
    -0.82
     he
    -0.81
     ORGANIC
    -0.81
     són
    -0.81
    POSITIVE LOGITS
    sowie
    0.95
    Inhalts
    0.94
    Verbindung
    0.92
    FUENTES
    0.91
    太大
    0.91
    旼
    0.90
    딪
    0.90
    Transk
    0.90
    𝘬
    0.89
     городов
    0.86
    Activations Density 0.019%

    No Known Activations